{"id":"https://openalex.org/W4375869271","doi":"https://doi.org/10.1109/icassp49357.2023.10096382","title":"Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videos","display_name":"Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videos","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869271","doi":"https://doi.org/10.1109/icassp49357.2023.10096382"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078220957","display_name":"Daizong Liu","orcid":"https://orcid.org/0000-0001-8179-4508"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daizong Liu","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8333806991577148},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6070595383644104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5829306840896606},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.5469250679016113},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.536579966545105},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5295197367668152},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4886839687824249},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47407451272010803},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4521775245666504},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4090571105480194},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2480822205543518},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.12093693017959595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8333806991577148},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6070595383644104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5829306840896606},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.5469250679016113},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.536579966545105},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5295197367668152},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4886839687824249},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47407451272010803},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4521775245666504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4090571105480194},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2480822205543518},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.12093693017959595},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1924770834","https://openalex.org/W2111078031","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2337252826","https://openalex.org/W2493916176","https://openalex.org/W2948958195","https://openalex.org/W2963017553","https://openalex.org/W2963916161","https://openalex.org/W3034743747","https://openalex.org/W3092739351","https://openalex.org/W3096935578","https://openalex.org/W3101429639","https://openalex.org/W3108225446","https://openalex.org/W3175082063","https://openalex.org/W3176471072","https://openalex.org/W3203995540","https://openalex.org/W4214542306","https://openalex.org/W4221148502","https://openalex.org/W4304080717","https://openalex.org/W4304086137","https://openalex.org/W4312295550","https://openalex.org/W4312941859","https://openalex.org/W4320008746","https://openalex.org/W4382462317","https://openalex.org/W6620707391","https://openalex.org/W6640212811","https://openalex.org/W6703281212","https://openalex.org/W6847780693"],"related_works":["https://openalex.org/W4389782456","https://openalex.org/W2903371384","https://openalex.org/W4302773889","https://openalex.org/W3084841567","https://openalex.org/W3008700642","https://openalex.org/W4288045581","https://openalex.org/W2884270194","https://openalex.org/W2969679616","https://openalex.org/W2966369713","https://openalex.org/W2963646814"],"abstract_inverted_index":{"Temporal":[0],"sentence":[1,21],"localization":[2],"in":[3,13,75,145,157],"videos":[4],"(TSLV)":[5],"aims":[6],"to":[7,18,52,59,65,99,109,123,139],"retrieve":[8],"the":[9,31,61,68,146,158],"most":[10],"interested":[11],"segment":[12],"an":[14],"untrimmed":[15],"video":[16,151],"according":[17],"a":[19,80,104,119,132,170],"given":[20],"query.":[22],"However,":[23],"almost":[24],"of":[25,127,150],"existing":[26],"TSLV":[27],"approaches":[28],"suffer":[29],"from":[30,97],"same":[32],"limitations:":[33],"(1)":[34],"They":[35,57],"only":[36],"focus":[37],"on":[38,162],"either":[39],"frame-level":[40],"or":[41],"object-level":[42,98],"visual":[43,115,120,125],"representation":[44],"learning":[45],"and":[46,84,93,148,153],"corresponding":[47],"correlation":[48,155],"reasoning,":[49,116,131],"but":[50],"fail":[51],"integrate":[53],"them":[54],"both;":[55],"(2)":[56],"neglect":[58],"leverage":[60,124,141],"rich":[62],"semantic":[63,130,133,142,159],"contexts":[64],"further":[66],"benefit":[67],"query":[69,95,112],"reasoning.":[70],"To":[71],"address":[72],"these":[73],"issues,":[74],"this":[76],"paper,":[77],"we":[78,102,117],"propose":[79],"novel":[81],"Hierarchical":[82],"Visual-":[83],"Semantic-Aware":[85],"Reasoning":[86],"Network":[87],"(HVSARN),":[88],"which":[89],"enables":[90],"both":[91],"visual-":[92],"semantic-aware":[94],"reasoning":[96,156],"frame-level.":[100],"Specifically,":[101],"present":[103],"new":[105,171],"graph":[106,121,134],"memory":[107,122,135],"mechanism":[108],"perform":[110,154],"visual-semantic":[111],"reasoning:":[113],"For":[114,129],"design":[118],"information":[126],"video;":[128],"is":[136],"also":[137],"introduced":[138],"explicitly":[140],"knowledge":[143],"contained":[144],"classes":[147],"attributes":[149],"objects,":[152],"space.":[160],"Experiments":[161],"three":[163],"datasets":[164],"demonstrate":[165],"that":[166],"our":[167],"HVSARN":[168],"achieves":[169],"state-of-the-art":[172],"performance.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}